Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction

Dan Feng Hong; Naoto Yokoya; Xiao Xiang Zhu

doi:10.1109/IGARSS.2016.7729001

Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction

Dan Feng Hong, Naoto Yokoya, Xiao Xiang Zhu

Chair of Data Science in Earth Observation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

12 Scopus citations

Abstract

Manifold learning has been successfully applied to hyperspectral dimensionality reduction to embed nonlinear and nonconvex manifolds in the data. However, dimensionality reduction by manifold learning is sensitive to non-uniform data distribution and the selection of neighbors. To address the two issues to some extents, in this work a new manifold framework based on locality linear embedding (LLE), namely local normalization and local feature selection (LNLFS), is proposed. Classification is explored as a potential application to validate the proposed algorithm. Classification accuracy using data obtained using different dimensionality reduction methods is evaluated and compared, while applying two kinds of strategies for selecting the training and test samples: random sampling and region-based sampling. Experimental results show the classification accuracy obtained with LNLFS is superior to state-of-the-art dimensionality reduction methods.

Original language	English
Title of host publication	2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	40-43
Number of pages	4
ISBN (Electronic)	9781509033324
DOIs	https://doi.org/10.1109/IGARSS.2016.7729001
State	Published - 1 Nov 2016
Event	36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, China Duration: 10 Jul 2016 → 15 Jul 2016

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2016-November

Conference

Conference	36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
Country/Territory	China
City	Beijing
Period	10/07/16 → 15/07/16

Keywords

dimensionality reduction
hyperspectral image
local feature selection
local normalization
manifold learning
non-uniform data distribution

Access to Document

10.1109/IGARSS.2016.7729001

Cite this

Hong, D. F., Yokoya, N., & Zhu, X. X. (2016). Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings (pp. 40-43). Article 7729001 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2016.7729001

Hong, Dan Feng ; Yokoya, Naoto ; Zhu, Xiao Xiang. / Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction. 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 40-43 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{a31a515bb1804047850f2e42d7edd502,

title = "Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction",

abstract = "Manifold learning has been successfully applied to hyperspectral dimensionality reduction to embed nonlinear and nonconvex manifolds in the data. However, dimensionality reduction by manifold learning is sensitive to non-uniform data distribution and the selection of neighbors. To address the two issues to some extents, in this work a new manifold framework based on locality linear embedding (LLE), namely local normalization and local feature selection (LNLFS), is proposed. Classification is explored as a potential application to validate the proposed algorithm. Classification accuracy using data obtained using different dimensionality reduction methods is evaluated and compared, while applying two kinds of strategies for selecting the training and test samples: random sampling and region-based sampling. Experimental results show the classification accuracy obtained with LNLFS is superior to state-of-the-art dimensionality reduction methods.",

keywords = "dimensionality reduction, hyperspectral image, local feature selection, local normalization, manifold learning, non-uniform data distribution",

author = "Hong, {Dan Feng} and Naoto Yokoya and Zhu, {Xiao Xiang}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 ; Conference date: 10-07-2016 Through 15-07-2016",

year = "2016",

month = nov,

day = "1",

doi = "10.1109/IGARSS.2016.7729001",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "40--43",

booktitle = "2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings",

}

Hong, DF, Yokoya, N & Zhu, XX 2016, Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction. in 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings., 7729001, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2016-November, Institute of Electrical and Electronics Engineers Inc., pp. 40-43, 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016, Beijing, China, 10/07/16. https://doi.org/10.1109/IGARSS.2016.7729001

Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction. / Hong, Dan Feng; Yokoya, Naoto; Zhu, Xiao Xiang.
2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 40-43 7729001 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction

AU - Hong, Dan Feng

AU - Yokoya, Naoto

AU - Zhu, Xiao Xiang

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Manifold learning has been successfully applied to hyperspectral dimensionality reduction to embed nonlinear and nonconvex manifolds in the data. However, dimensionality reduction by manifold learning is sensitive to non-uniform data distribution and the selection of neighbors. To address the two issues to some extents, in this work a new manifold framework based on locality linear embedding (LLE), namely local normalization and local feature selection (LNLFS), is proposed. Classification is explored as a potential application to validate the proposed algorithm. Classification accuracy using data obtained using different dimensionality reduction methods is evaluated and compared, while applying two kinds of strategies for selecting the training and test samples: random sampling and region-based sampling. Experimental results show the classification accuracy obtained with LNLFS is superior to state-of-the-art dimensionality reduction methods.

AB - Manifold learning has been successfully applied to hyperspectral dimensionality reduction to embed nonlinear and nonconvex manifolds in the data. However, dimensionality reduction by manifold learning is sensitive to non-uniform data distribution and the selection of neighbors. To address the two issues to some extents, in this work a new manifold framework based on locality linear embedding (LLE), namely local normalization and local feature selection (LNLFS), is proposed. Classification is explored as a potential application to validate the proposed algorithm. Classification accuracy using data obtained using different dimensionality reduction methods is evaluated and compared, while applying two kinds of strategies for selecting the training and test samples: random sampling and region-based sampling. Experimental results show the classification accuracy obtained with LNLFS is superior to state-of-the-art dimensionality reduction methods.

KW - dimensionality reduction

KW - hyperspectral image

KW - local feature selection

KW - local normalization

KW - manifold learning

KW - non-uniform data distribution

UR - http://www.scopus.com/inward/record.url?scp=85007433790&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2016.7729001

DO - 10.1109/IGARSS.2016.7729001

M3 - Conference contribution

AN - SCOPUS:85007433790

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 40

EP - 43

BT - 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016

Y2 - 10 July 2016 through 15 July 2016

ER -

Hong DF, Yokoya N, Zhu XX. Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 40-43. 7729001. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2016.7729001

Local manifold learning with robust neighbors selection for hyperspectral dimensionality reduction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this